Infection Check

Safety check for prompt injection. Scans agent output for credential leaks, data theft, and other malicious behavior before tool execution.

Check Mode

Thoughts : Analyze reasoning/thoughts only (faster — runs in parallel with response generation).
Complete : Analyze full response including tool arguments (slower, more thorough).

Thoughts (faster)Complete (thorough)

Model

Which model runs the security analysis.

Utility modelMain model

Max Clarifications

Maximum clarification rounds before auto-terminate.

History Size

Recent conversation messages to include as context for the check.

Security Audit Prompt

System prompt for the security check model. Customize detection rules and output format.